Related papers: Libra: Accelerating Socket I/O via Programmable Se…

High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems.The…

In recent years, enterprise Solid-State Drives (SSDs) are used in the caching layer of high-performance servers to close the growing performance gap between processing units and storage subsystem. SSD-based I/O caching is typically not…

Code coverage analysis plays an important role in the software testing process. More recently, the remarkable effectiveness of coverage feedback has triggered a broad interest in feedback-guided fuzzing. In this work, we introduce bcov, a…

Modern large multicore systems often run multiple workloads that share CPUs under schedulers such as Linux CFS. To keep CPUs busy, these schedulers load-balance runnable work, causing each workload to execute on many cores. This weakens…

Recent literature has found that an effective method to customize or further improve large language models (LLMs) is to add dynamic adapters, such as low-rank adapters (LoRA) with Mixture-of-Experts (MoE) structures. Though such dynamic…

The rapidly evolving landscape of AI and machine learning workloads has widened the gap between high-level domain operations and efficient hardware utilization. Achieving near-peak performance still demands deep hardware expertise-experts…

High-quality human-annotated data is crucial for modern deep learning pipelines, yet the human annotation process is both costly and time-consuming. Given a constrained human labeling budget, selecting an informative and representative data…

Patch reviewing is critical for software development, especially in distributed open-source development, which highly depends on voluntary work, such as Linux. This paper studies the past 10 years of patch reviews of the Linux memory…

Basic Linear Algebra Subprograms (BLAS) is a core library in scientific computing and machine learning. This paper presents FT-BLAS, a new implementation of BLAS routines that not only tolerates soft errors on the fly, but also provides…

For modern flash-based SSDs, the performance overhead of internal data migrations is dominated by the data transfer time, not by the flash program time as in old SSDs. In order to mitigate the performance impact of data migrations, we…

Porting applications to new hardware or programming models is a tedious and error prone process. Every help that eases these burdens is saving developer time that can then be invested into the advancement of the application itself instead…

In this paper, we propose LoopLynx, a scalable dataflow architecture for efficient LLM inference that optimizes FPGA usage through a hybrid spatial-temporal design. The design of LoopLynx incorporates a hybrid temporal-spatial architecture,…

Hardware accelerators such as Graphics Processing Units (GPUs), Intel Xeon Phi co-processors (PHIs), and Field-Programmable Gate Arrays (FPGAs) are now ubiquitous in extreme-scale high performance computing (HPC), cloud, and Big data…

Modern distributed pipelined query engines either do not support intra-query fault tolerance or employ high-overhead approaches such as persisting intermediate outputs or checkpointing state. In this work, we present write-ahead lineage, a…

Configuring stream processing systems for efficient performance, especially in cloud-native deployments, is a challenging and largely manual task. We present an experiment-driven approach for automated configuration optimization that…

The fast-growing large scale language models are delivering unprecedented performance on almost all natural language processing tasks. However, the effectiveness of large language models are reliant on an exponentially increasing number of…

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…

Although deep learning-based personalized recommendation systems provide qualified recommendations, they strain data center resources. The main bottleneck is the embedding layer, which is highly memory-intensive due to its sparse, irregular…

Lightweight Tunnels (LWTs) in the Linux kernel enable efficient per-route tunneling and are widely used by protocols such as In Situ Operations, Administration, and Maintenance (IOAM), Segment Routing over IPv6 (SRv6), and Routing Protocol…

Traditional executable delivery models pose challenges for IoT devices with limited storage, necessitating the download of complete executables and dependencies. Network solutions like NFS, designed for data files, encounter high IO…